DreamFusion
Generate 3D assets from text
DreamFusion launched on September 30, 2022 with 84 votes, #496 of 3,464 launches that month and more than 75% of that year's launches. The site was still online in September 2026, 4 years on.
What it does
Given a caption, DreamFusion generates relightable 3D objects with high-fidelity appearance, depth, and normals. Objects are represented as a Neural Radiance Field and leverage a pretrained text-to-image diffusion prior such as Imagen.
DreamFusion: Text-to-3D using 2D Diffusion, 2022.
--> Recent breakthroughs in text-to-image synthesis have been driven by diffusion models trained on billions of image-text pairs. Adapting this approach to 3D synthesis would require large-scale datasets of labeled 3D assets and efficient architectures for denoising 3D data, neither of which currently exist. In this work, we circumvent these limitations by using a pretrained 2D text-to-image diffusion model to perform text-to-3D synthesis. We introduce a loss based on probability density distillation that enables the use of a 2D diffusion model as a prior for optimization of a parametric image generator. Using this loss in a DeepDream-like procedure, we optimize a randomly-initialized 3D…from dreamfusion3d.github.io
Does a similar job
all alternatives →
Generative Fill with AI and 3D2023 · github.com · ▲360Hey all, You've probably seen projects that add objects to an image from a style or text prompt, like InteriorAI (levelsio) and Adobe Firefly. The prevalent issue with these diffusion-based inpainting approaches is that they don't yet have great conditioning on lighting, perspective, and structure. You'll often get incorrect or generic shadows; warped-looking objects; and distorted backgrounds. What is Fill 3D? Fill 3D is an exploration on doing generative fill in 3D to render ultra-realistic results that harmonize with the background image, using industry-standard path tracing, akin to…
D-ID's Creative Reality™ Studio2022 · studio.d-id.com · ▲1,069Use generative AI to create future-facing videos
MAI-Image-2.5Jun 2026 · microsoft.ai · ▲241Hey HN I’ve been experimenting with different image generation tools for months — but I kept running into the same problems: slow generation, repeated outputs, and limited artistic control. That’s why I built MAI-Image-1, Microsoft’s latest AI image generation model designed for creators, designers, and developers who need fast, realistic results without sacrificing flexibility. What makes MAI-Image-1 different: Ultra-realistic rendering — it accurately captures light, texture, and natural shadows. Lightning-fast generation — create detailed images in seconds. No style lock-in — experiment…
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 20d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 28d ago · world.pixverse.video
Source: Product Hunt launch ↗
Launched alongside, September 2022
the whole month →- IM
Life & fun · 2022 · dogbunnypuzzle.com
A couple of years ago, I had an interesting idea. What if there was a marketplace where all the underlying tech was open-source? The order management system, the storefront, customer support, etc. The marketplace would simply connect to the seller’s infra instead of locking them in. If, for some reason, the seller is removed from the marketplace, their software stays with them and they can continue accepting orders directly. This model can be used to disrupt any marketplace from AirBNB to UberEats: building tech for home renters and restaurants and later, leveraging that to build a competing…
Dev tools · 2022 · openship.org
